Safety-aligned large language models (LLMs) sometimes falsely refuse pseudo-harmful
prompts, like" how to kill a mosquito," which are actually harmless. Frequent false refusals …

Large language models (LLMs) are vulnerable to adversarial attacks that can elicit harmful
responses. Defending against such attacks remains challenging due to the opacity of …

LLMs have shown remarkable capabilities, but precisely controlling their response behavior
remains challenging. Existing activation steering methods alter LLM behavior …

Despite the recent advancements in Large Language Models (LLMs), which have
significantly enhanced the generative capabilities for various NLP tasks, LLMs still face …

Large language models (LLMs) have demonstrated remarkable capabilities across a wide
range of natural language processing tasks. However, their tendency to exhibit sycophantic …

Building pluralistic AI requires designing models that are able to be shaped to represent a
wide range of value systems and cultures. Achieving this requires first being able to evaluate …

Steering methods provide a practical approach to controlling large language models by
applying steering vectors to intermediate activations, guiding outputs toward desired …

Activation engineering is becoming increasingly popular as a means of online control of
large language models (LLMs). In this work, I extend the idea of active steering with vectors …